Semantic sports video analysis

Approaches and new applications

Baoxin Li, Ibrahim Sezan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

33 Citations (Scopus)

Abstract

We show that event-based semantic analysis of sports video can be achieved through two major classes of methods: approaches using deterministic reasoning and approaches depending on probabilistic inference. Deterministic approaches depend on an explicit description of an event and an explicit representation of the event in terms of low-level aural-visual features that can be automatically detected. Probabilistic approaches are based on some proper state/transition models whose parameters are learnt through labeled training sequences. We first discuss the pros and cons of the two classes of approaches. Next, we present algorithms of these two types for a new application, automatic analysis of coaching video (which is different from sports broadcast programs that have been subject of most prior work).

Original languageEnglish (US)
Title of host publicationIEEE International Conference on Image Processing
Pages17-20
Number of pages4
Volume1
StatePublished - 2003
Externally publishedYes
EventProceedings: 2003 International Conference on Image Processing, ICIP-2003 - Barcelona, Spain
Duration: Sep 14 2003Sep 17 2003

Other

OtherProceedings: 2003 International Conference on Image Processing, ICIP-2003
CountrySpain
CityBarcelona
Period9/14/039/17/03

Fingerprint

Sports
Semantics

ASJC Scopus subject areas

  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Li, B., & Sezan, I. (2003). Semantic sports video analysis: Approaches and new applications. In IEEE International Conference on Image Processing (Vol. 1, pp. 17-20)

Semantic sports video analysis : Approaches and new applications. / Li, Baoxin; Sezan, Ibrahim.

IEEE International Conference on Image Processing. Vol. 1 2003. p. 17-20.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Li, B & Sezan, I 2003, Semantic sports video analysis: Approaches and new applications. in IEEE International Conference on Image Processing. vol. 1, pp. 17-20, Proceedings: 2003 International Conference on Image Processing, ICIP-2003, Barcelona, Spain, 9/14/03.
Li B, Sezan I. Semantic sports video analysis: Approaches and new applications. In IEEE International Conference on Image Processing. Vol. 1. 2003. p. 17-20
Li, Baoxin ; Sezan, Ibrahim. / Semantic sports video analysis : Approaches and new applications. IEEE International Conference on Image Processing. Vol. 1 2003. pp. 17-20
@inproceedings{2727a09127fa4c9fb1880ec77c369b8e,
title = "Semantic sports video analysis: Approaches and new applications",
abstract = "We show that event-based semantic analysis of sports video can be achieved through two major classes of methods: approaches using deterministic reasoning and approaches depending on probabilistic inference. Deterministic approaches depend on an explicit description of an event and an explicit representation of the event in terms of low-level aural-visual features that can be automatically detected. Probabilistic approaches are based on some proper state/transition models whose parameters are learnt through labeled training sequences. We first discuss the pros and cons of the two classes of approaches. Next, we present algorithms of these two types for a new application, automatic analysis of coaching video (which is different from sports broadcast programs that have been subject of most prior work).",
author = "Baoxin Li and Ibrahim Sezan",
year = "2003",
language = "English (US)",
volume = "1",
pages = "17--20",
booktitle = "IEEE International Conference on Image Processing",

}

TY - GEN

T1 - Semantic sports video analysis

T2 - Approaches and new applications

AU - Li, Baoxin

AU - Sezan, Ibrahim

PY - 2003

Y1 - 2003

N2 - We show that event-based semantic analysis of sports video can be achieved through two major classes of methods: approaches using deterministic reasoning and approaches depending on probabilistic inference. Deterministic approaches depend on an explicit description of an event and an explicit representation of the event in terms of low-level aural-visual features that can be automatically detected. Probabilistic approaches are based on some proper state/transition models whose parameters are learnt through labeled training sequences. We first discuss the pros and cons of the two classes of approaches. Next, we present algorithms of these two types for a new application, automatic analysis of coaching video (which is different from sports broadcast programs that have been subject of most prior work).

AB - We show that event-based semantic analysis of sports video can be achieved through two major classes of methods: approaches using deterministic reasoning and approaches depending on probabilistic inference. Deterministic approaches depend on an explicit description of an event and an explicit representation of the event in terms of low-level aural-visual features that can be automatically detected. Probabilistic approaches are based on some proper state/transition models whose parameters are learnt through labeled training sequences. We first discuss the pros and cons of the two classes of approaches. Next, we present algorithms of these two types for a new application, automatic analysis of coaching video (which is different from sports broadcast programs that have been subject of most prior work).

UR - http://www.scopus.com/inward/record.url?scp=0345529040&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0345529040&partnerID=8YFLogxK

M3 - Conference contribution

VL - 1

SP - 17

EP - 20

BT - IEEE International Conference on Image Processing

ER -